Restore score= in [END] stdout per updated spec 1118dd7 Running verified anshumanatrey commited on about 18 hours ago
Fix HF_TOKEN handling, [END] always emitted, add openenv tag 3e7a0ef verified anshumanatrey commited on about 18 hours ago
Fix [END] stdout format — remove extra score= field db7b6af verified anshumanatrey commited on about 18 hours ago
Sync: compliance mapping, anti-gaming, 55 tests, mandatory stdout format, pivoting+compliance weights c1a5935 verified anshumanatrey commited on about 19 hours ago
Update: three-tier reasoning benchmark, real LLM scores, industry stats, pivoting score a92d3db verified anshumanatrey commited on 5 days ago